© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71991
    Prev
    Next
    INDEX
    Explanations

    Gy unit of radiation dose

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects the unit "Gy" which is used to measure radiation dose.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on the radiation‐dose unit “Gy,” i.e. mentions of doses measured in Grays.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MUCH
    -2.48
     Possibly
    -2.44
    ſelves
    -2.42
     Importantly
    -2.39
     Ensuring
    -2.39
     Allowing
    -2.39
    лерея
    -2.38
     Effectively
    -2.36
     Speaking
    -2.34
    </h2>
    -2.31
    POSITIVE LOGITS
    -
    2.92
    1
    2.75
     ausein
    2.61
    та
    2.52
    在
    2.42
     gefahren
    2.42
    s
    2.38
    ’
    2.38
    unjung
    2.34
    一开始
    2.34
    Activations Density 0.005%

    No Known Activations